{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:15:50Z","timestamp":1729617350773,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,4]]},"DOI":"10.1109\/wiopt.2007.4480049","type":"proceedings-article","created":{"date-parts":[[2008,4,2]],"date-time":"2008-04-02T18:57:29Z","timestamp":1207162649000},"page":"1-8","source":"Crossref","is-referenced-by-count":16,"title":["Reinforcement Learning for Routing in Ad Hoc Networks"],"prefix":"10.1109","author":[{"given":"Petteri","family":"Nurmi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Learning in extensive-form games II, experimentation and Nash equilibrium","author":"fudenberg","year":"1994","journal-title":"Tech Rep"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s001990050244"},{"key":"ref31","first-page":"1064","article-title":"Monte Carlo POMDPs","volume":"12","author":"thrun","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1007\/978-3-540-30496-8_13","article-title":"Advanced detection of selfish or malicious nodes in ad hoc networks","volume":"3313","author":"kargl","year":"2004","journal-title":"Proceedings of 1st European Workshop on Security in Ad-Hoc and Sensor Networks (ESAS 2004) ser Lecture Notes in Computer Science"},{"key":"ref37","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","author":"bowling","year":"2001","journal-title":"Proceedings of the 17th International Joint Conference on Artificial Intelligence (IJCAI)"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"journal-title":"Neural Networks A Comprehensive Foundation","year":"1998","author":"haykin","key":"ref35"},{"key":"ref34","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2003.1208918"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/AICT-ICIW.2006.2"},{"journal-title":"The Evolution of Cooperation","year":"1984","author":"axelrod","key":"ref11"},{"key":"ref12","article-title":"Non-cooperative forwarding in ad-hoc networks","author":"altman","year":"2004","journal-title":"Proceedings of the 15th IEEE International Symposium on Personal Indoor and Mobile Radio Communications"},{"key":"ref13","article-title":"Modelling cooperation in mobile ad hoc networks: a formal description of selfishness","author":"urpi","year":"2003","journal-title":"Proc Workshop Modeling and Optimization in Mobile Ad Hoc and Wireless Networks (WiOpt)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025146013151"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2003.1209220"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/939010.939011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LANMAN.2004.1338430"},{"key":"ref18","first-page":"1679","article-title":"SIP: a secure incentive protocol against selfishness in mobile ad hoc networks","volume":"3","author":"zhang","year":"2004","journal-title":"Proceedings of the Wireless Communications and Networking Conference (WCNC)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/345910.345955"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2002.993520"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2005.846390"},{"key":"ref27","first-page":"22","article-title":"Energy conserving routing in wireless ad hoc networks","author":"chang","year":"2000","journal-title":"Proceedings of the 19th Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM)"},{"key":"ref3","first-page":"945","article-title":"Predictive q-routing: A memory-based reinforcement learning approach to adaptive traffic control","volume":"8","author":"choi","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/571697.571723"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2004.833122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2006.34"},{"article-title":"Selfish routing","year":"2002","author":"roughgarden","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/380752.380883"},{"key":"ref2","first-page":"671","article-title":"Packet routing in dynamically changing networks: A reinforcement learning approach","volume":"6","author":"boyan","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/90.477727"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1190195.1190200"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-35612-9_9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/513800.513828"},{"key":"ref21","article-title":"Observation-based cooperation enforcement in ad hoc networks","author":"bansal","year":"2003","journal-title":"Computing Research Repository (CoRR)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/RAWCON.1998.709135"},{"key":"ref23","first-page":"825","article-title":"SORI: A secure and objective reputation-based incentive scheme for ad-hoc networks","author":"he","year":"2002","journal-title":"Proceedings of the Wireless Communications and Networking Conference (WCNC)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/49.779917"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1145\/288235.288286","article-title":"Power-aware routing in mobile ad hoc networks","author":"singh","year":"1998","journal-title":"Proceedings of the 4th annual ACM\/IEEE international conference on Mobile computing and networking (MOBI-COM)"}],"event":{"name":"2007 5th International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks (WiOpt)","start":{"date-parts":[[2007,4,16]]},"location":"Limassol, Cyprus","end":{"date-parts":[[2007,4,20]]}},"container-title":["2007 5th International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks and Workshops"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4479865\/4480002\/04480049.pdf?arnumber=4480049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,9]],"date-time":"2019-05-09T20:33:12Z","timestamp":1557433992000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4480049\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,4]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/wiopt.2007.4480049","relation":{},"subject":[],"published":{"date-parts":[[2007,4]]}}}